Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

• Published in: Journal of cheminformatics Vol. 13; no. 1; pp. 93 - 16
• Main Authors: Chen, Jiarui, Si, Yain-Whar, Un, Chon-Wai, Siu, Shirley W. I.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 27.11.2021; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Algorithms; Animal experimentation; Animal research; Artificial neural networks; Biocompatibility; Chemical compounds; Chemical toxicity; Chemistry; Chemistry and Materials Science; Computational Biology/Bioinformatics; Computational linguistics; Computer Applications in Chemistry; Deep learning; Documentation and Information in Chemistry; Drug discovery; Ethical standards; Experiments; Graph convolutional neural network; In vivo methods and tests; Language processing; Learning algorithms; Machine learning; Mean teacher; Methodology; Natural language interfaces; Neural networks; Predictions; Semi-supervised learning; Social networks; Success; Theoretical and Computational Chemistry; Tox21; Toxicity; Toxicity testing; Toxicology; Deep learning; Chemical toxicity; Semi-supervised learning; Mean teacher; Graph convolutional neural network; ADMET; Tox21

As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these ex...